Stanford

Tech Crunch - May 1st, 2025
Score 7.2

Study accuses LM Arena of helping top AI labs game its benchmark

AI benchmark fairness questioned: LM Arena accused of bias in leaderboard tests

Tech Crunch - Apr 4th, 2025
Score 7.2

OpenAI’s models ‘memorized’ copyrighted content, new study suggests

Study reveals OpenAI models trained on copyrighted content, raising legal concerns.

Previous Next

Showing 1 to 2 of 2 results